Statistical testing is a cornerstone of data analysis. It provides a structured way to make decisions or draw conclusions about a population based on information gathered from a sample.

When you collect data, you rarely have access to every possible observation in the group you care about. Instead, you gather a subset — a sample — and use statistical tests to infer what is likely true about the entire group, or population. This process is known as statistical inference.

The purpose of statistical testing is to help you answer questions such as:

• Is there evidence that a new product increases sales?
• Are two groups of users behaving differently?

By applying statistical tests, you can evaluate whether observed differences or relationships in your sample data are likely to reflect real effects in the broader population, or if they could have occurred just by chance.

The logic behind statistical testing is rooted in probability. You start by making an assumption about the population, called the null hypothesis. You then use your sample data to assess whether this assumption should be rejected. If the sample provides strong enough evidence, you may conclude that the effect you observe is statistically significant and not simply the result of random variation.

Key Terms

• Population: the entire group you want to learn about;
• Sample: a subset of the population that you actually observe or analyze;
• Parameter: a fixed value that describes a characteristic of the population (such as the true mean or proportion);
• Statistic: a value calculated from the sample, used to estimate a population parameter.